#coding-agents

51 posts

2026 - November

1 post

Creating a Framework for AI with AI: REA Launcher SDK

After building seven launchers with AI agents to modernize old racing games, I extracted what they had in common into a framework, rea-launcher-sdk. I explain why a framework is extracted from several projects and never designed up front, how migrating the launchers found bugs in the SDK and in the launchers themselves, the built-in techniques (a test before every fix, snapshots, headless tests, CI, agents that run the game and debug crash dumps), the test and coverage numbers for each project, the two new launchers built straight from the SDK, and the step by step for anyone to build a launcher for their favorite game with the agent of their choice.

2026 - October

3 posts

I Self-Published My Own Book/e-book: Competent Enough

I published my book about AI, for free, in EPUB and PDF: the blog's 131 posts from 2026, almost half a million words, reorganized into 20 chapters, 10 appendices, a glossary and more than 300 references. This text is the technical backstage: the inventory with a hash per post, the contract every agent read before writing, the parallel drafts, the invisible per-paragraph marker that ties the book to the blog, the checker that fails a chapter with an error, what the fact-check caught wrong in my own posts, and the Quarto, Typst and Pandoc pipeline that generates everything. It's a preview: open an issue if you find a mistake.

LLMs + Agents = competent enough

A synthesis of what I've been measuring and writing: LLMs converged. The transformer architecture got near the ceiling, the parameter war is over, and the leap everyone felt in 2025 and 2026 came from the agentic harness (tool calling, prompt caching, long sessions), not from a base intelligence orders of magnitude larger. I retell the timeline from 2019 onward with sources, explain why the agent allows a less dense model, and why that's already competent enough to automate real software engineering.

2026 - September

10 posts

Talking a Bit About My AI Skills

Agent skills are just prompts in text files. I keep 25 in my my-skills repo, from pr-audit to fact-check, and they have already closed over a thousand PRs and issues across my projects. The recommendation: don't copy somebody else's skill, build your own.

2026 - August

2 posts

2026 - July

6 posts

2026 - June

3 posts

2026 - May

5 posts

2026 - April

6 posts

2026 - March

2 posts

2026 - February

1 post

2026 - January

6 posts

2025 - May

2 posts

2025 - April

4 posts